SAM.gov

search_exclusions

Read-only

Check SAM.gov public exclusion/debarment records by UEI, CAGE, or name. Filters combine. Searches the dated public extract, which is not a complete exclusion history; inactive or terminated historical records may be absent. Every result identifies the source file and date. No matches in the extract is not a live clearance or eligibility determination; confirm current status on SAM.gov.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_exclusions"
  }
}

Input Schema

Name	Required	Description
`uei`	No	12-character Unique Entity ID; exact match.
`page`	No
`size`	No
`country`	No	3-character ISO alpha-3 country code, e.g. USA.
`cage_code`	No	5-character CAGE; exact match.
`entity_name`	No	Partial firm or individual name; punctuation, spacing, ampersands and common company suffixes are normalized, including first/middle/last names. Zero results include separately labeled possible name matches; names alone do not confirm identity.
`classification`	No
`state_province`	No
`exclusion_program`	No
`excluding_agency_code`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only/non-destructive safety, and the description adds substantial context the annotations cannot: the data comes from a dated public extract, inactive or terminated records may be missing, every result carries its source file and date, and absence is not an eligibility determination. That is unusually rich disclosure for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each carrying distinct information: capability, filter behavior, data-source limitation, result provenance, and the no-match caveat. The core capability is front-loaded and nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequately covers scope, caveats, and provenance for a 10-parameter, all-optional search with no output schema. The main remaining gap is how pagination and the ambiguous name-match fallback results should be interpreted, which the schema only partially explains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40% across 10 parameters, and the description only mentions three of the filter keys plus the fact that filters combine (AND semantics), which does add meaning. The enum filters (classification, exclusion_program, excluding_agency_code) and pagination are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource pair (check SAM.gov public exclusion/debarment records) and names the three key lookup identifiers (UEI, CAGE, name). The resource is inherently distinct from the entity/opportunity siblings, so an agent can select it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-not guidance: the extract is not a complete history and a no-match is not a clearance, so the agent knows to escalate to SAM.gov rather than treat a hit as authoritative. It also notes that filters combine. It does not explicitly contrast with search_entities for the same identifier, which keeps it below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SAM.gov tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.